This repository maintains the codes that are used in the exercises of the book Learn Keras for Deep Neural Networks
The book is a quick start guide for beginners to learn, understand and implement deep neural networks in a math and programming-friendly approach using Keras and Python. The book focuses on an end-to-end accelerated track delving into a holistic approach to develop supervised learning algorithms in regression and classification with practical business-centric use-cases implemented in Keras.
The overall book comprises of 3 sections with 2 chapters each.
Section 1, prepares the reader with all the necessary gears to get started on the fast track ride in deep learning.
Chapter 1 introduces the audience to the world of deep learning and its difference from machine learning, the choices of frameworks for deep learning, the Keras ecosystem.
Chapter 2, helps the reader get started with hands-on exercise in Keras, understanding the basic building blocks of deep learning and developing the first basic DNN.
Section 2, helps the reader embrace the core fundamentals in a simple lucid language while abstracting the math and the complexities of model training and validation with the least amount of code without compromising on flexibility, scale and the required sophistication.
In Chapter 3 and 4, the reader is demonstrated with real-life business problems that can be solved by supervised learning algorithms with deep neural networks. We tackle one use case for regression in Chapter 3 and another for classification in Chapter 4, leveraging popular Kaggle datasets. Both the use-cases, together, would help the reader understand the craft of designing, training, measuring and validating deep neural networks i.e. measuring performance and understanding the shortcomings and the means to circumvent them.
SEction 3, discussed model tuning and deploying and highlihgt the path forward for advanced deep learning topics.
In chapter 5, we discuss an interesting and challenging part of deep learning i.e. hyperparameter tuning; aiding the reader in further improving the models into building robust deep learning models. Finally, Chapter 6 – the conclusion, discusses the path ahead for the reader to further hone his skills in deep learning and discusses few areas of active development and research in Deep Learning. [Note, Chapter 6 would only make the user aware of the topics for the path ahead with a brief yet concise introduction and references for further reading].
At the end of the crash course, the reader will have a thorough understanding of the deep learning principles within the shortest time-frame and would have practical hands-on experience in developing enterprise-grade deep learning solutions in Keras.